© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77540
    Prev
    Next
    INDEX
    Explanations

    "to" infinitive phrases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pi
    -0.45
    PI
    -0.41
     Geografia
    -0.40
     оригіналу
    -0.39
    êt
    -0.39
     Omo
    -0.39
    imet
    -0.38
    ToBounds
    -0.38
    ível
    -0.38
    serviceWorker
    -0.37
    POSITIVE LOGITS
     resourceCulture
    1.09
    ThroughAttribute
    0.93
    AndEndTag
    0.84
    ValueStyle
    0.82
    دانشنامهٔ
    0.81
    AddTagHelper
    0.75
    setVerticalGroup
    0.74
     <=",
    0.73
    enterOuterAlt
    0.72
    Autoritní
    0.71
    Activations Density 0.009%

    No Known Activations